Search Results

This paper proposed a collision avoidance strategy that take over the control of ego vehicle when faced with urgent collision risk. To improve the applicability of collision avoidance strategy in complex scenarios, the theory of ICS (Inevitable Collision State) is introduced to evaluate the collision risk and compute the trigger flag of the system, and vehicle dynamic is taken into account when modeling ego vehicle to predict ego vehicle’s following moving. Vehicle specific characteristics including reaction time of the braking system and the braking force increasing process are taken into account. In order to reduce injury caused by collision accidents and minimize disruption to drivers, slight steering is added on top of emergency braking. The direction of the steering angle is determined according to IM (Imitating Maneuvers) The flow chart of the strategy is presented in the paper.

Research of Adaptive Cruise Control (ACC) is an important issue of intelligent vehicle (IV). As we all known, a real and experienced driver can control vehicle's speed very well under every traffic environment of ACC working. So a direct and feasible way for establishing ACC controller is to build a human-like longitudinal control algorithm with the simulation of driver behavior of speed control. In this paper, a novel fuzzy self-tuning control algorithm of ACC is established and this controller's parameters can be tuned on-line based on the evaluation indexes that can describe how the driver consider the quality of dynamical characteristic of vehicle longitudinal dynamics. With the advantage of the controller's parameter on-line self-tuning, the computational workload from matching design of ACC controller is also efficiently reduced.

Driving style and skill classification are of great significance in human-oriented advanced driver-assistance system (ADAS) development. In this paper, we propose Fully-Connected Deep Neural Networks (FC-DNN) to classify drivers’ styles and skills with naturalistic driving data. Followed by the data collection and pre-processing, FC-DNN with a series of deep learning optimization algorithms are applied. In the experimental part, the proposed model is validated and compared with other commonly used supervised learning methods including the k-nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), and multilayer perceptron (MLP). The results show that the proposed model has a higher Macro F1 score than other methods. In addition, we discussed the effect of different time window sizes on experimental results. The results show that the driving information of 1s can improve the final evaluation score of the model.

Advanced driver assistance systems (ADAS) are being developed for more and more complicated application scenarios, which often require more predictive strategies with better understanding of driving environment. Taking traffic vehicles’ maneuvers into account can greatly expand the beforehand time span for danger awareness. This paper presents a maneuver-based strategy to vehicle collision threat assessment. First, a maneuver-based trajectory prediction model (MTPM) is built, in which near-future trajectories of ego vehicle and traffic vehicles are estimated with the combination of vehicle’s maneuvers and kinematic models that correspond to every maneuver. The most probable maneuvers of ego vehicle and each traffic vehicles are modeled and inferred via Hidden Markov Models with mixture of Gaussians outputs (GMHMM). Based on the inferred maneuvers, trajectory sets consisting of vehicles’ position and motion states are predicted by kinematic models.

The conventional radar modeling methods for automotive applications were either function-based or physics-based. The former approach was mainly abstracted as a solution of the intersection between geometric representations of radar beam and targets, while the latter one took radar detection mechanism into consideration by means of “ray tracing”. Although they each has its unique advantages, they were often unrealistic or time-consuming to meet actual simulation requirements. This paper presents a combined geometric and physical modeling method on millimeter-wave radar systems for Frequency Modulated Continuous Wave (FMCW) modulation format under a 3D simulation environment. With the geometric approach, a link between the virtual radar and 3D environment is established. With the physical approach, on the other hand, the ideal target detection and measurement are contaminated with noise and clutters aimed to produce the signals as close to the real ones as possible.

Lane detection is one of the most important part in ADAS because various modules (i.e., LKAS, LDWS, etc.) need robust and precise lane position for ego vehicle and traffic participants localization to plan an optimal routine or make proper driving decisions. While most of the lane detection approaches heavily depend on tedious pre-processing and great amount of assumptions to get reasonable result, the robustness and efficiency are deteriorated. To address this problem, a novel framework is proposed in this paper to realize robust and real-time lane detection. This framework consists of two branches, where canny edge detection and Progressive Probabilistic Hough Transform (PPHT) are introduced in the first branch for efficient detection.

With the increasing number of urban cars, parking has become the primary problem that people face in daily life. Therefore, many scholars have studied the automatic parking system. In the existing research, most of the path planning methods use the combined path of arc and straight line. In this method, the path curvature is not continuous, which indirectly leads to the low accuracy of path tracking. The parking path designed using the fifth-order polynomial is continuous, but its curvature is too large to meet the steering constraints in some cases. In this paper, a continuous-curvature parking path is proposed. The parking path tracker based on Model Predictive Control (MPC) algorithm is designed under the constraints of the control accuracy and vehicle steering. Firstly, in order to make the curvature of the parking path continuous, this paper superimposes the fifth-order polynomial with the sigmoid function, and the curve obtained has the continuous and relatively small curvature.

Forecasting the motion of the leading vehicle is a critical task for connected autonomous vehicles as it provides an efficient way to model the leading-following vehicle behavior and analyze the interactions. In this study, a personalized time-series modeling approach for leading vehicle trajectory prediction considering different driving styles is proposed. The method enables a precise, personalized trajectory prediction for leading vehicles with limited inter-vehicle communication signals, such as vehicle speed, acceleration, space headway, and time headway of the front vehicles. Based on the learning nature of human beings that a human always tries to solve problems based on grouping and similar experience, three different driving styles are first recognized based on an unsupervised clustering with a Gaussian Mixture Model (GMM).

Threat assessment (TA) method is vital in the decision-making process of intelligent vehicles (IVs), especially for ADAS systems. In the research of TA, the probabilistic threat assessment (PTA) method is acting an increasing role, which can reduce the uncertainties of driver’s maneuvers. However, the driver behavior model (DBM) used in present PTA methods was mainly constructed by limited data or simple functions, which is not entirely reasonable and may affect the performance of the TA process. This work aims to utilize crash data extracted from Event Data Recorder (EDR) to establish more accurate DBM and improve the current PTA method in rear-end situations. EDR data with responsive maneuvers were firstly collected, which were then employed to construct the initial DBM (I-DBM) model by using the multivariate Gaussian distribution (MGD) framework. Besides, the model was further subdivided into six parts by two important risk indicators, Time-to-collision (TTC) and velocity.

Proper tire pressure is very important for multiple driving performance of a car, and it is necessary to monitor and warn the abnormal tire pressure online. Indirect Tire Pressure Monitoring System (TPMS) monitors the tire pressure based on the wheel speed signals of Anti-lock Braking System (ABS). In this paper, an indirect TPMS method is proposed to estimate the tire pressure according to its resonance frequency of circumferential vibration. Firstly, the errors of ABS wheel speed sensor system caused by the machining tolerance of the tooth ring are estimated based on the measured wheel speed using Recursive Least Squares (RLS) algorithm and the measuring errors are eliminated from the wheel speed signal. Then, the data segments with drive train torsional vibration are found out and eliminated by the methods of correlation analysis.

The global adaptive cruise control (ACC) market is expected to witness a compound annual growth rate of 18.3% during the forecast period to reach $15,290 million by 2023 [1]. The driver uses an ACC system to reduce the driving burden and improve safety. The ACC mode in a car is fixed, but different drivers have different driving habits. This paper will verify this through experiments and divide drivers into three categories according to the drivers’ driving habits. Therefore, we will design a personalized ACC, wherein an ACC system, under the same working conditions, can have different acceleration and deceleration to meet the needs of different types of drivers. Therefore, this paper collects driver data, analyzes model data and identifies its parameters, and finally verifies the different effects of personalized ACC through simulation.

Studying traffic accidents by using naturalistic driving data has become increasingly appealing for its potential benefits in improving road safety. This paper presents findings from a field test which has been conducted on 50 taxis in the urban areas of Beijing for 10 months using Video Drive Recorders (VDRs). The VDR used in this study could record the information of vehicle front view video, vehicle states, as well as driver operations immediately before and after an event. The drivers were given no specific instructions during the test, and the instrumentation for data collection was unobtrusive. Important safety-relevant parameters, such as vehicle speed, pre-event maneuver, time headway, time-to-collision, and driver reaction time, were calculated with precision. Based on these parameters, an analysis into features and causes of rear-end conflicts is performed.

The intelligent unmanned ground vehicle (UGV) motorcade system consisting of one leader and n − 1 followers is considered. The safety distance between the front and rear UGVs is treated as the control target. Since the safety distance constraint is a unilateral constraint, the state transformation is needed. Hence, a piecewise type conversion function is formulated to serve for the transformation of the original inequality constraint. The system equation is further expressed by the new state. We assume that the input of the leading UGV is known. Combined with the uncertainty evaluation, a class of collaborative controls for the following UGVs is proposed to deal with the uncertainty with unknown bound. The effectiveness of the designed control is verified by both Lyapunov stability theory and simulations. Both theoretical and simulation results illustrate that the longitudinal safety, stability and global behavior of the intelligent motorcade system are guaranteed.

Driver steering feature clustering aims to understand driver behavior and the decision-making process through the analysis of driver steering data. It seeks to comprehend various steering characteristics exhibited by drivers, providing valuable insights into road safety, driver assistance systems, and traffic management. The primary objective of this study is to thoroughly explore the practical applications of various clustering algorithms in processing driver steering data and to compare their performance and applicability. In this paper, principal component analysis was employed to reduce the dimension of the selected steering feature parameters. Subsequently, K-means, fuzzy C-means, the density-based spatial clustering algorithm, and other algorithms were used for clustering analysis, and finally, the Calinski-Harabasz index was employed to evaluate the clustering results. Furthermore, the driver steering features were categorized into lateral and longitudinal categories.

The platooning of connected automated vehicles (CAV) possesses the significant potential of reducing energy consumption in the Intelligent Transportation System (ITS). Moreover, with the rapid development of eco-driving technology, vehicle platooning can further enhance the fuel efficiency by optimizing the efficiency of the powertrain. Since road grade is a main factor that affects the energy consumption of a vehicle, the estimation of the road grade with high accuracy is the key factor for a connected vehicle platoon to optimize energy consumption using vehicle-to-vehicle (V2V) communication. Commonly, the road grade is quantified by single consumer grade global positioning system (GPS) with the geodetic height data which is rough and in the meter-level, increasing the difficulty of precisely estimating the road grade.

Traffic congestions are increasingly severe in urban areas, especially at the merging areas of the ramps and the arterial roads. Because of the complex conflict relationship of the vehicles in ramps and arterial roads in terms of time-spatial constraints, it is challenging to coordinate the motion of these vehicles, which may easily cause congestions at the merging areas. The connected and automated vehicles (CAVs) provides potential opportunities to solve this problem. A centralized merging control method for CAVs is proposed in this paper, which can organize the traffic movements in merging areas efficiently and safely. In this method, the merging control model is built to formulate the vehicle coordination problem in merging areas, which is then transformed to the discrete nonlinear optimization form. A simulation model is built to verify the proposed method.

Human driving behavior's inherent variability, randomness, individual differences, and dynamic vehicle-road situations give human-machine cooperative (HMC) driving considerable uncertainty, which affects the applicability and effectiveness of HMC control in complex scenes. To overcome this challenge, we present a novel data-enabled game output regulation approach for HMC driving. Firstly, a global human-vehicle-road (HVR) model is established considering the varied driver's steering characteristic parameters, such as delay time, preview time, and steering gain, as well as the uncertainty of tire cornering stiffness and variable road curvature disturbance. The robust output regulation theory has been employed to ensure the global DVR system's closed-loop stability, asymptotic tracking, and disturbance rejection, even with an unknown driver's internal state. Secondly, an interactive shared steering controller has been designed to provide personalized driving assistance.

Lane-changing systems have been developed and applied to improve environmental adaptability of advanced driver assistant system (ADAS) and driver comfort. Lane-changing control consists of three steps: decision making, trajectory planning and trajectory tracking. Current methods are not perfect due to weaknesses such as high computation cost, low robustness to uncertainties, etc. In this paper, a novel lane changing control method is proposed, where lane-changing behavior is analogized to parallel parking behavior. In the perspective of host vehicle with lane-changing intention, the space between vehicles in the target adjacent lane can be regarded as dynamic parking space. A decision making and path planning algorithm of parallel parking is adapted to deal with lane change condition. The adopted algorithm based on rules checks lane-changing feasibility and generates desired path in the moving reference system at the same speed of vehicles in target lane.

As one of advanced driver assistance systems (ADAS), automatic parking system has great market prospect and application value. In this paper, based on an intelligent vehicle platform, an automatic parking system is designed by using multi-point preview theory. The vehicle kinematics model was established, based on Ackermann steering principle. By analyzing working conditions of parallel parking, complex constraint condition of parking trajectory is established and reference trajectory based on sine wave is proposed. In addition, combined with multi-point preview theory, the design of trajectory following controller for automatic parking is completed. The cost function is designed, which consider the trajectory following effect and the degree of easy handling. The optimization of trajectory following control is completed by using the cost function.

According to the statistics of National Highway Traffic Safety Administration, driver’s cognitive distraction, which is usually caused by drivers using mobile phones, has become one of the main causes of traffic accidents. To solve this problem and guarantee the safety of man-vehicle-road system, the most critical work is to improve the accuracy of driver’s cognitive state detection. In this paper, a novel driver’s cognitive state detecting method based on LightGBM (Light Gradient Boosting Machine) is proposed. Firstly, cognitive distraction experiments of making calls are carried out on a driving simulator to collect vehicle states, eye tracking and EEG (electron encephalogram) data simultaneously and feature extraction is conducted. Then a classifier considering road and individual characteristics used for detecting cognitive states is trained based on LightGBM algorithm, with 3 predefined cognitive states including concentration, ordinary distraction and extreme distraction.